Discriminative training on language model
نویسندگان
چکیده
Statistical language models have been successfully applied to a lot of problems, including speech recognition, handwriting, Chinese pinyin-input etc. In recognition, a statistical language model, such as the trigram model, is used to predict the probabilities of hypothesized word sequences. The traditional method that relies on distribution estimation is sub-optimal when the assumed distribution form is inapplicable, and that “optimality” in distribution estimation does not automatically translate into “optimality” in classifier design. This paper proposed a discriminative training method to minimize the error rate of recognizer rather than estimate the distribution of training data. Furthermore, lexicon is also optimized to minimize the error rate of the decoder through discriminative training. Compared to the traditional LM building method, our system achieves a 5%-25% reduction in error rate.
منابع مشابه
Interdependence of Language Models and Discriminative Training
In this paper, the interdependence of language models and discriminative training for large vocabulary speech recognition is investigated. In addition, a constrained recognition approach using word graphs is presented for the efficient determination of alternative word sequences for discriminative training. Experiments have been carried out on the ARPA Wall Street Journal corpus. The recognitio...
متن کاملDiscriminative Training and Support V Language Call Ro
In natural language call routing, callers are routed to desired departments based on natural spoken responses to an open-ended “How may I direct your call?” prompt. Natural language call classification can be performed using support vector machines (SVMs) or the popular vector-based model used in information retrieval. We recently demonstrate how discriminative training is powerful to improve a...
متن کاملDiscriminative training of language model classifiers
We show how discriminative training methods, namely the Maximum Mutual Information and Maximum Discrimination approach, can be adopted for the training of N-gram language models used as clas-siiers working on symbol strings. By estimating the model parameters according to a discriminative objective function instead of Maximum Likelihood, the emphasis is not put on the exact modeling of each cla...
متن کاملLanguage Identification and Multilingual Speech Recognition Using Discriminatively Trained Acoustic Models
We perform language identification experiments for four prominent South-African languages using a multilingual speech recognition system. Specifically, we show how successfully Afrikaans, English, Xhosa and Zulu may be identified using a single set of HMMs and a single recognition pass. We further demonstrate the effect of language identification-specific discriminative acoustic model training ...
متن کاملRisk-Based Semi-Supervised Discriminative Language Modeling for Broadcast Transcription
This paper describes a new method for semi-supervised discriminative language modeling, which is designed to improve the robustness of a discriminative language model (LM) obtained from manually transcribed (labeled) data. The discriminative LM is implemented as a log-linear model, which employs a set of linguistic features derived from word or phoneme sequences. The proposed semi-supervised di...
متن کاملDiscriminative Training of a Neural Network Statistical Parser
Discriminative methods have shown significant improvements over traditional generative methods in many machine learning applications, but there has been difficulty in extending them to natural language parsing. One problem is that much of the work on discriminative methods conflates changes to the learning method with changes to the parameterization of the problem. We show how a parser can be t...
متن کامل